A. Karaali, CR. Jung, "Edge-Based Defocus Blur Estimation with Adaptive Scale Selection", IEEE Transactions on Image Processing (TIP 2018), 2018
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
EdgeAwareInterpolation.m
LICENSE
README.md
blur_estimate_our.m
convertion.mat
demo_one_image_1.m
demo_one_image_2.m
demo_one_image_3.m
g1x.m
g1y.m
image_01.png
image_05.png
image_22.png
map_01.mat
map_05.mat
map_22.mat

README.md

TIP2018-Edge-Based-Defocus-Blur-Estimation-With-Adaptive-Scale-Selection

A. Karaali, CR. Jung, "Edge-Based Defocus Blur Estimation with Adaptive Scale Selection", IEEE Transactions on Image Processing (TIP 2018), 2018

Any papers using this code should cite the paper accordingly.

The software has been tested under Matlab R2015a.

After unpacking the file and downloading the required functions of the DOMAIN TRANSFORM FILTERING from (http://www.inf.ufrgs.br/~eslgastal/DomainTransform/), you can then run "demo_one_image_1.m", "demo_one_image_2.m" or "demo_one_image_3.m" in the root directory.

As is, the code produces the results given as the first experimental setting with dataset which is provided in ('Non-parametric blur map regression for depth of field extension'). In order to reach the dataset, you should contact with the author of this paper. The code here includes just 3 sample images from this dataset.

Please also report any bug to alixkaraali[at_sign]gmail[dot_sign]com